Hyperspectral image classification is a research hotspot in the field of hyperspectral image processing and application. Classification models predict the class of each pixel by analyzing the spectral and spatial information of each pixel and compare it to the actual features. In the hyperspectral classification task, the spatial context information of the data can be used to improve the classification accuracy, so this paper uses the powerful learning ability of 3D-CNN to extract effective spectral and spatial features into hyperspectral images, and then fuses the extracted spectra and spatial features to enhance the flow between different levels of the network, thereby improving the classification efficiency. Although CNN operations can mine deeper feature information as the network deepens, CNN is ineffective in modeling long-distance dependencies, so consider combining CNN with attention mechanisms. This combination can focus on the local position of the given information, assign corresponding weights to it, emphasize the key features in the feature map, adjust the global information of the attention statistics image through weight re-annotation, retain the features that are more conducive to the classification task, and improve the representation ability of extracted features. But the common attention mechanism is to calculate the average globally, that is, the pixel values of the entire image block, inevitably introducing information from different categories of pixels around it, which is not needed in classification tasks. Another spectral attention mechanism based on the center pixel provides weight values that ignore the effects of surrounding pixels in the same category. Therefore, a simple spectral attention mechanism in the central region is proposed, in which the central region is selected with the central pixel as the reference and the surrounding 3×3 range as the central region, on the one hand, the range contains certain spectral information of the same category, and on the other hand, the interference of different categories of pixels is reduced as much as possible. The spectral attention mechanism in the central region can minimize the influence of interfering pixels on spectral features while extracting as many effective spectral features as possible. Based on the spectral attention mechanism of the central region, this paper proposes a spectral spatial attention residual network for hyperspectral classification, which mainly includes spectral feature learning, spatial feature learning and classifier. The network first selects appropriately sized image blocks from hyperspectral images and then classifies them. Starting from balancing computing resources and overall accuracy, experimental comparison shows that the size of the image patch is uniformly 13×13. The spectral feature learning part includes 1 frequency spectral attention module and 1 spectral residual network module. The spectral attention module adopts the central spectral attention mechanism, which can effectively suppress redundant bands and increase the weight of important bands. The spectral features after the attention mechanism will be extracted by the spectral residual network module, and more spectral features can be extracted. Convolution kernels of 1×1×n do not affect the spatial structure when extracting spectral features while maintaining spatial correlation. The spatial feature learning component includes 1 spatial attention module and 2 spatial residual network modules. The spatial attention module can obtain the important spatial information of the pixels to be classified, and use the spatial residual network to extract its spatial information. Add a hop connection between each module in the network to connect the presentation layer of the hierarchical features into a continuous residual block to mitigate the loss of accuracy. Finally, these rich spectral and spatial features are sent to the classifier to obtain the final classification result. The proposed algorithm is compared with the latest algorithm on four public datasets. Indicators and visualization results verify the superiority of the proposed algorithm.